Hi! We've received your issue and please be patient to get responded. We will arrange technicians to answer your questions as soon as possible. Please make sure that you have posted enough message to demo your request. You may also check out the API ， FAQ and Github Issue to get the answer.Have a nice day!
2条答案
按热度按时间qc6wkl3g1#
您好，我们已经收到了您的问题，会安排技术人员尽快解答您的问题，请耐心等待。请您再次检查是否提供了清晰的问题描述、复现代码、环境&版本、报错信息等。同时，您也可以通过查看 官网文档 、 常见问题 、 历史Issue 来寻求解答。祝您生活愉快～
Hi! We've received your issue and please be patient to get responded. We will arrange technicians to answer your questions as soon as possible. Please make sure that you have posted enough message to demo your request. You may also check out the API ， FAQ and Github Issue to get the answer.Have a nice day!
58wvjzkj2#
经过一番尝试，在输出里看到 in_dims.size() == 4 || in_dims.size() == 5 test error，网上搜索了一下，看到这篇issue： #7336
于是我用netron查看我的nb文件，发现输入确实是3个，但是java代码里面 inputTensor确实少了，于是修改如下：
// Set input shape
Tensor inputTensor1 = getInput(1);
inputTensor1.resize(inputShape);
Tensor sizeTensor = getInput(0);
sizeTensor.resize(new long[] {1,2});
Tensor scaleTensor = getInput(2);
scaleTensor.resize(new long[] {1,2});
再运行，不出错，有预测结果了，但是结果的坐标里面，也就是outputTensor.getFloatData()，里面的top,left值有，但是right和bottom的值为0，请问这是哪里的问题啊？